© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 14735
    Prev
    Next
    INDEX
    Explanations

    african american colleges universities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ーん
    -1.52
     conquer
    -1.49
    抵达
    -1.46
    是这样的
    -1.45
    ごちそう
    -1.45
    ひた
    -1.45
    过来了
    -1.44
    ご馳走
    -1.41
    私に
    -1.41
     nôtre
    -1.40
    POSITIVE LOGITS
     african
    1.54
    <td>
    1.41
     are
    1.38
     afro
    1.34
     only
    1.32
    мую
    1.24
    焦
    1.23
     African
    1.23
     graden
    1.23
     numai
    1.22
    Activations Density 0.198%

    No Known Activations